Improving mgmt methylation status prediction of glioblastoma through optimizing radiomics features using genetic algorithm-based machine learning approach

HIGHLIGHTS

SUMMARY

Upon downloading the pre-processed and segmented multimodal MRI (mMRI) features from the TCIA public database, a two-stage radiomics feature selection approach was conducted on the mMRI feature set to identify the most informative features for MGMT methylation status classification purpose. The Can- cer Genome Atlas (TCGA)-GBM24 collections were downloaded from Bakas et_al25. Totally 704 radiomics features were obtained from Bakas et_al25 and can be classified into seven categories. The categories include first-order statistical features (intensity), volumetric f­eatures26, textural features describing the statistical relationship between image voxels (e_g, gray-level . . .

 



If you want to have access to all the content you need to log in!

Thanks :)

Username or Email

Password

Remember me

Lost your password?

If you don't have an account, you can create one here.